# DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors

arXiv: https://arxiv.org/abs/2204.02890 · HTML: https://mlsanity.com/paper/2204.02890/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 56 references that are in the map.
- First posted on arXiv 6 Apr 2022.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos](https://mlsanity.com/paper/1701.05384/) (2017)
- [Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments](https://mlsanity.com/paper/1707.05733/) (2017)
- [Bayesian Fusion of Multi-Band Images](https://mlsanity.com/paper/1307.5996/) (2013)
- [ME R-CNN: Multi-Expert R-CNN for Object Detection](https://mlsanity.com/paper/1704.01069/) (2017)
- [Detect2Rank : Combining Object Detectors Using Learning to Rank](https://mlsanity.com/paper/1412.7957/) (2014)
- [Dynamic Belief Fusion for Object Detection](https://mlsanity.com/paper/1511.03183/) (2015)
- [IOD-CNN: Integrating Object Detection Networks for Event Recognition](https://mlsanity.com/paper/1703.07431/) (2017)
- [DOD-CNN: Doubly-injecting Object Information for Event Recognition](https://mlsanity.com/paper/1811.02910/) (2018)
- [S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition](https://mlsanity.com/paper/1902.04051/) (2019)

## Built on by (most cited first, 3 of 3)

- [Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion](https://mlsanity.com/paper/2410.12592/) (2024)
- [EPL: Evidential Prototype Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2404.06181/) (2024)
- [Informative Data Selection with Uncertainty for Multi-modal Object Detection](https://mlsanity.com/paper/2304.11697/) (2023)

## Abstract (arXiv)

In this paper, we propose a novel and highly practical score-level fusion approach called dynamic belief fusion (DBF) that directly integrates inference scores of individual detections from multiple object detection methods. To effectively integrate the individual outputs of multiple detectors, the level of ambiguity in each detection score is estimated using a confidence model built on a precision-recall relationship of the corresponding detector. For each detector output, DBF then calculates the probabilities of three hypotheses (target, non-target, and intermediate state (target or non-target)) based on the confidence level of the detection score conditioned on the prior confidence model of individual detectors, which is referred to as basic probability assignment. The probability distributions over three hypotheses of all the detectors are optimally fused via the Dempster's combination rule. Experiments on the ARL, PASCAL VOC 07, and 12 datasets show that the detection accuracy of the DBF is significantly higher than any of the baseline fusion approaches as well as individual detectors used for the fusion.